Robust Subject-Independent P300 Waveform Classification via Signal Pre-Processing and Deep Learning

Brain Computer Interfaces (BCIs) are capable of processing neural stimuli using electroencephalogram (EEG) measurements to aid communication capabilities. Yet, BCIs often require extensive calibration steps in order to be tuned to specific users. In this work, we develop a subject independent P300 classification framework, which eliminates the need for user-specific calibration. We begin by employing a series of pre-processing steps, where, among other steps, we consider different trial averaging methodologies and various EEG electrode configurations. We then consider three distinct deep learning architectures and two linear machine learning models as P300 signal classifiers. Through evaluation on three datasets, and in comparison to three benchmark P300 classification frameworks, we find that averaging up to seven trials while using eight specific electrode channels on a two-layered convolutional neural network (CNN) leads to robust subject independent P300 classification. In this capacity, our method achieves greater than a 0.20 gain in AUC in comparison to prior P300 classification methods. In addition, our proposed framework is computationally efficient with training time gains of greater than 3×, compared to linear machine learning models, and online evaluation time speedups of up to 2× compared to benchmark methods.

[1]  Theerawit Wilaiprasitporn,et al.  Consumer Grade EEG Measuring Sensors as Research Tools: A Review , 2020, IEEE Sensors Journal.

[2]  R. Hornero,et al.  EEG-Inception: A Novel Deep Convolutional Neural Network for Assistive ERP-Based Brain-Computer Interfaces , 2020, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  Zeki Oralhan,et al.  3D Input Convolutional Neural Networks for P300 Signal Detection , 2020, IEEE Access.

[4]  Abdelhak Mahmoudi,et al.  Efficient detection of P300 using Kernel PCA and support vector machine , 2014, 2014 Second World Conference on Complex Systems (WCCS).

[5]  Seong-Whan Lee,et al.  Subject-Independent Brain–Computer Interfaces Based on Deep Convolutional Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Hubert Cecotti,et al.  Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Hema A. Murthy,et al.  Single Trial P300 Classification Using Convolutional LSTM and Deep Learning Ensembles Method , 2018, IHCI.

[8]  Ekapol Chuangsuwanich,et al.  Universal Joint Feature Extraction for P300 EEG Classification Using Multi-Task Autoencoder , 2018, IEEE Access.

[9]  Erwei Yin,et al.  Adding Real-Time Bayesian Ranks to Error-Related Potential Scores Improves Error Detection and Auto-Correction in a P300 Speller , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[10]  Shengjin Wang,et al.  Exploiting EEG Channel Correlations in P300 Speller Paradigm for Brain-Computer Interface , 2016, IEICE Trans. Inf. Syst..

[11]  Yu Liu,et al.  A Simple Convolutional Neural Network for Accurate P300 Detection and Character Spelling in Brain Computer Interface , 2018, IJCAI.

[12]  Jonathan R Wolpaw,et al.  Brain–computer interface systems: progress and prospects , 2007, Expert review of medical devices.

[13]  F. Piccione,et al.  P300-based brain computer interface: Reliability and performance in healthy and paralysed participants , 2006, Clinical Neurophysiology.

[14]  Yih-Choung Yu,et al.  Exploring P300-based Biometric for Individual Identification Based on Convolutional Neural Networks , 2018, 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).

[15]  S Thomas George,et al.  Visual P300 Mind-Speller Brain-Computer Interfaces: A Walk Through the Recent Developments With Special Focus on Classification Algorithms , 2020, Clinical EEG and neuroscience.

[16]  Monica Fira.  Detection of P300 in a BCI Speller , 2011, ICHIT.

[17]  D. B. Ryan,et al.  Evaluating brain-computer interface performance using color in the P300 checkerboard speller , 2017, Clinical Neurophysiology.

[18]  Christoph Reichert,et al.  Convolutional Neural Networks for Decoding of Covert Attention Focus and Saliency Maps for EEG Feature Visualization , 2019 .

[19]  Chunyan Miao,et al.  3D CNN Based Automatic Diagnosis of Attention Deficit Hyperactivity Disorder Using Functional and Structural MRI , 2017, IEEE Access.

[20]  Mohammed Yeasin,et al.  Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks , 2015, ICLR.

[21]  G.F. Inbar,et al.  An improved P300-based brain-computer interface , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[22]  Wolfram Burgard,et al.  Deep learning with convolutional neural networks for EEG decoding and visualization , 2017, Human brain mapping.

[23]  Theerawit Wilaiprasitporn,et al.  Affective EEG-Based Person Identification Using the Deep Learning Approach , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[24]  Jing Xiao,et al.  A Novel Three-Dimensional P300 Speller Based on Stereo Visual Stimuli , 2018, IEEE Transactions on Human-Machine Systems.

[25]  R. Fazel-Rezai,et al.  Analysis of P300 Classifiers in Brain Computer Interface Speller , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  E. W. Sellers,et al.  Toward enhanced P300 speller performance , 2008, Journal of Neuroscience Methods.

[27]  Andrzej Cichocki,et al.  The Study of Generic Model Set for Reducing Calibration Time in P300-Based Brain–Computer Interface , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[28]  Alex Graves,et al.  Supervised Sequence Labelling , 2012 .

[29]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[30]  E. Donchin,et al.  A P300-based brain–computer interface: Initial tests by ALS patients , 2006, Clinical Neurophysiology.

[31]  Seif Eldawlatly,et al.  An Intermixed Color Paradigm for P300 Spellers: A Comparison with Gray-Scale Spellers , 2017, 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS).

[32]  Stephen M. Gordon,et al.  EEGNet: A Compact Convolutional Neural Network for EEG-based Brain-Computer Interfaces , 2021 .

[33]  K. Gardner,et al.  Recruitment of p300/CBP in p53-Dependent Signal Pathways , 1997, Cell.

[34]  Ramesh Maddula,et al.  Deep Recurrent Convolutional Neural Networks for Classifying P300 BCI signals , 2017, GBCIC.

[35]  Sourav Kundu,et al.  Fusion of Convolutional Neural Networks for P300 Based Character Recognition , 2019, 2019 International Conference on Information Technology (ICIT).

[36]  Chris Berka,et al.  Comparison of Medical and Consumer Wireless EEG Systems for Use in Clinical Trials , 2017, Front. Hum. Neurosci..

[37]  Amin Zollanvari,et al.  Learning Discriminative Spatiospectral Features of ERPs for Accurate Brain–Computer Interfaces , 2019, IEEE Journal of Biomedical and Health Informatics.

[38]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[39]  Ren Xu,et al.  Developing a Novel Tactile P300 Brain-Computer Interface With a Cheeks-Stim Paradigm , 2020, IEEE Transactions on Biomedical Engineering.

[40]  Somdip Dey,et al.  SoCodeCNN: Program Source Code for Visual CNN Classification Using Computer Vision Methodology , 2019, IEEE Access.

[41]  Touradj Ebrahimi,et al.  An efficient P300-based brain–computer interface for disabled subjects , 2008, Journal of Neuroscience Methods.